Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 6181
    Prev
    Next
    INDEX
    Explanations

    references to vampires and their traits as depicted in literature and folklore

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    vampires and vampire lore

    np_acts-logits-general · gemini-2.0-flash

    vampire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngrx
    -0.43
    islation
    -0.39
     linkovi
    -0.38
    brenner
    -0.38
     túi
    -0.37
     Públicas
    -0.37
    InputBorder
    -0.37
    ∭
    -0.37
     reten
    -0.37
    小人
    -0.37
    POSITIVE LOGITS
     vampire
    1.21
     vampires
    1.10
     Vampire
    0.98
     Vamp
    0.96
    vampire
    0.92
    Vampire
    0.91
    Dracula
    0.90
     Dracula
    0.90
    Vamp
    0.85
     vamp
    0.84
    Activations Density 0.281%

    No Known Activations